Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to statistical or mathematical models and parameters in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.18
    windowFixed
    -1.09
     Baillargeon
    -1.01
    AsUp
    -1.00
    хьтан
    -0.97
    Rüyada
    -0.93
     Paglinawan
    -0.90
     auffi
    -0.89
     poffe
    -0.88
     Chriftian
    -0.85
    POSITIVE LOGITS
    mathrm
    1.97
    setcounter
    0.70
    mathbf
    0.66
     it
    0.63
    enumi
    0.60
     an
    0.60
     they
    0.59
     and
    0.58
     a
    0.57
     />
    0.57
    Act Density 0.038%

    No Known Activations